Commit Graph

37 Commits

Author SHA1 Message Date
Robert Watson
eb956cd041 Use if_maddr_rlock()/if_maddr_runlock() rather than IF_ADDR_LOCK()/
IF_ADDR_UNLOCK() across network device drivers when accessing the
per-interface multicast address list, if_multiaddrs.  This will
allow us to change the locking strategy without affecting our driver
programming interface or binary interface.

For two wireless drivers, remove unnecessary locking, since they
don't actually access the multicast address list.

Approved by:	re (kib)
MFC after:	6 weeks
2009-06-26 11:45:06 +00:00
Attilio Rao
1abcdbd127 When user_frac in the polling subsystem is low it is going to busy the
CPU for too long period than necessary.  Additively, interfaces are kept
polled (in the tick) even if no more packets are available.
In order to avoid such situations a new generic mechanism can be
implemented in proactive way, keeping track of the time spent on any
packet and fragmenting the time for any tick, stopping the processing
as soon as possible.

In order to implement such mechanism, the polling handler needs to
change, returning the number of packets processed.
While the intended logic is not part of this patch, the polling KPI is
broken by this commit, adding an int return value and the new flag
IFCAP_POLLING_NOCOUNT (which will signal that the return value is
meaningless for the installed handler and checking should be skipped).

Bump __FreeBSD_version in order to signal such situation.

Reviewed by:	emaste
Sponsored by:	Sandvine Incorporated
2009-05-30 15:14:44 +00:00
Pyun YongHyeon
767fb36c3a NVIDIA MCP controllers have no Rx buffer alignment restrictions.
Remove PAGE_SIZE alignment used in Rx buffer DMA tag creation. The
alignment restriction was used in old local jumbo allocator and
nfe(4) switched to UMA backed page allocator for jumbo frame.

This change should fix jumbo buffer allocation failure.

Reported by:	Pascal Braun ( pascal.braun <> continum dot net )
2009-05-25 00:56:01 +00:00
Pyun YongHyeon
69d6a6aafc Fix a typo.
Submitted by:	clemens fischer via Shigeaki Tagashira
2008-12-20 00:04:04 +00:00
Pyun YongHyeon
17d022beb2 Add hardware MAC statistics support. Register information was
obtained from Linux forcedeth driver.
While I'm here move creating a sysctl node for process_limit to
function nfe_sysctl_node().

Tested by:	"Arno J. Klaassen" < arno <at> heho dot snv dot jussieu dot fr >
2008-10-03 03:58:16 +00:00
Pyun YongHyeon
be38e61a52 Add device ids for MCP77/79 and set appropriate support flags.
Obtained from:  OpenBSD
PR:		kern/127529
2008-10-01 00:17:54 +00:00
Pyun YongHyeon
b7e548dc72 Add support for MCP73 chips.
Tested by:	"Daan Vreeken [PA4DAN]" ( Danovitsch AT vitsch DOT net )
MFC after:	1 week
2008-04-10 01:25:09 +00:00
Pyun YongHyeon
3a5d5a69ce Nuke local jumbo allocator and switch to use of UMA backed page
allocator for jumbo frame. Also remove unneeded jlist lock which
is no longer required to protect jumbo buffers.
With these changes jumbo frame performance of nfe(4) was slightly
increased and users should not encounter jumbo buffer allocation
failure anymore.
2008-03-06 01:47:53 +00:00
Poul-Henning Kamp
cf827063a9 Give MEXTADD() another argument to make both void pointers to the
free function controlable, instead of passing the KVA of the buffer
storage as the first argument.

Fix all conventional users of the API to pass the KVA of the buffer
as the first argument, to make this a no-op commit.

Likely break the only non-convetional user of the API, after informing
the relevant committer.

Update the mbuf(9) manual page, which was already out of sync on
this point.

Bump __FreeBSD_version to 800016 as there is no way to tell how
many arguments a CPP macro needs any other way.

This paves the way for giving sendfile(9) a way to wait for the
passed storage to have been accessed before returning.

This does not affect the memory layout or size of mbufs.

Parental oversight by:	sam and rwatson.

No MFC is anticipated.
2008-02-01 19:36:27 +00:00
John Baldwin
304a4c6fb1 - Retire npe_defrag(), gem_defrag(), msk_defrag(), nfe_defrag(), and
re_defrag() and use m_collapse() instead.
- Replace a reference to ath_defrag() in a comment in if_wpi.c with
  m_collapse().
2008-01-17 23:37:47 +00:00
Pyun YongHyeon
6a087a8722 Fix function prototype for device_shutdown method. 2007-11-22 02:45:00 +00:00
Sam Leffler
cbb1d39de7 use the private task q thread instead of the shared system thread
Reviewed by:	yongari
MFC after:	1 week
2007-11-16 15:51:47 +00:00
Pyun YongHyeon
144e07f0e7 Apparently some NVIDIA NICs store ethernet address in reverse order
while other variants have inorder ethernet address for the same
chipset. Override ethernet address ordering if we already know how
it was stored. This fixes the use of inversed ethernet address on
MCP67.

Submitted by:	ariff
MFC after:	3 days
2007-11-06 01:01:38 +00:00
Pyun YongHyeon
0142a9b171 During boot(before setting IP address) PHY can generate link state
change interrupt if the link is established with link parter. However
interrupt handler didn't acknowledge the interrupt if nfe(4) was not
running at the time of interrupt delivery. This caused endless
interrupt generation. Fix the bug by acknowledging the interrupt
regardless of running state of the driver.

PR:	kern/116295
Submitted by:	Mark Derbyshire (mark At taom dot com)
Approved by:	re (kensmith)
2007-09-14 05:12:25 +00:00
Pyun YongHyeon
50c55b295c Fix typo.
Pointed out:	marius
Approved by:	re (bmah)
2007-09-14 01:28:18 +00:00
Pyun YongHyeon
8b590ad2d1 Don't fail on device attach if jumbo frame support was unsuccessful.
Because nfe(4) hardware doesn't support SG on Rx path, supporting
jumbo frame requires very large contiguous kernel memory(i.e. several
mega bytes). In case of lack of contiguous kernel memory that
allocation request may always fail. However nfe(4) can operate on normal
sized MTU frames, so go ahead and just disable jumbo frame support.
While I'm here add a new tunable "hw.nfe.jumbo_disable" to disable
jumbo frame support.
In nfe_poll, make sure to invoke correct Rx handler.

Approved by:	re (kensmith)
2007-07-24 01:11:00 +00:00
Pyun YongHyeon
a272ea16ed The maximum size of the sum of all segment lengths in a given DMA mapping
should be 65535 + link layer headers.

Pointed out by:	gallatin
2007-06-12 10:51:47 +00:00
Pyun YongHyeon
1c88901672 Increase a maximum segment size of DMA to 4096. Previously it used
MCLBYTES for the segment size but it used too many Tx descriptors in
TSO case.
While I'm here adjust maximum size of the sum of all segment lengths
in a given DMA mapping to 65535, the maximum size, in bytes, of a IP
packet.
2007-06-12 02:35:01 +00:00
Pyun YongHyeon
aab5582f0a Bring overhauled nfe(4) into tree.
o s/printf/device_printf/g
o Nuke OpenBSDism.
o Nuke NetBSD/OpenBSD specific DMA sync operations.(we don't have a way
   to sync a single descriptor within a DMA map.)
o Remove recursive mutex.
o bus_dma(9) clean up.
o 40bit DMA address support.
o Add protection for Rx map load failure.
o Fix a long standing bug for watchdog timeout. [1]
o Add additional protections, missing Tx completion interrupt, losing
   start Tx command, for watchdog timeout.
o Switch to taskqueue(9) API to handle interrupts.
o Use our own timer for watchdog instead of if_watchdog/if_timer
   interface.
o Advertise VLAN header length/capability correctly to upper layer.
o Remove excessive kernel stack consumption in nfe_encap().
o Handle highly fragmented mbuf chains correctly.
o Enable etherenet address reprogramming with ifconfig(8).
o Add ALTQ/TSO, MSI/MSIX support.
o Increased Rx ring to 256 descriptors from 128.
o Align Tx/Rx descriptor ring on sizeof(struct nfe_desc64) boundary.
o Remove alignment restrictions on Tx/Rx buffers.
o Rewritten jumbo frame support code.
o Add support for hardware assistend VLAN tag insertion/stripping.
o Add support for Tx/Rx flow control based on patches from Peer Chen. [2]
o Add a routine that detects whether ethernet address swap routines is
   required. [3]
o Add a workaround that take MAC/PHY out of power down mode.
o Add suspend/resume support.
o style(9) and code clean up.

Special thanks to Shigeaki Tagashira, the original porter of nfe(4),
who submitted lots of patches, performed uncountable number of
regression tests and maintained nfe(4) for a long time. Without his
enthusiastic help and support I could never have completed this
overhauling task.

The only weak point of nfe(4) compared to nve(4) is instability of
manual half-duplex media selection on certain hardwares(auto sensing
media type should work for all cases, though). This was a long
standing bug of nfe(4) and I still have no idea why it doesn't work
on some hardwares.

Obtained from:	OpenBSD [1]
Submitted by:	Peer Chen < pchen at nvidia dot com > [2], [3]
Reviewed by:	Shigeaki Tagashira < shigeaki AT se DOT hiroshima-u DOT ac DOT jp >
Tested by:	Shigeaki Tagashira, current
Discussed with:	current
Silence from:	obrien
2007-06-12 02:16:02 +00:00
Christian S.J. Peron
59a0d28bac Catch up the rest of the drivers with the ether_vlan_mtap modifications.
If these drivers are setting M_VLANTAG because they are stripping the
layer 2 802.1Q headers, then they need to be re-inserting them so any
bpf(4) peers can properly decode them.

It should be noted that this is compiled tested only.

MFC after:	3 weeks
2007-03-04 03:38:08 +00:00
Paolo Pisati
ef544f6312 o break newbus api: add a new argument of type driver_filter_t to
bus_setup_intr()

o add an int return code to all fast handlers

o retire INTR_FAST/IH_FAST

For more info: http://docs.freebsd.org/cgi/getmsg.cgi?fetch=465712+0+current/freebsd-current

Reviewed by: many
Approved by: re@
2007-02-23 12:19:07 +00:00
David E. O'Brien
7597761a50 Fix TX/RX checksum offload.
Submitted by:	Peer Chen at nVIDIA
2006-11-27 04:47:27 +00:00
David E. O'Brien
30ce3a1229 Reformat to KNF after revision 1.12. 2006-11-27 00:23:59 +00:00
David E. O'Brien
6124fe214e Fix the jumbo frame support.
Submitted by:	Peer Chen at nVIDIA (reworked by me)
2006-11-27 00:16:47 +00:00
David E. O'Brien
a0f9e922a7 Grrr. new .vimrc file is really giving me trouble.. get the whitespace right. 2006-11-27 00:10:00 +00:00
David E. O'Brien
96058696ac Fix editor fatfingering in rev 1.9. 2006-11-27 00:05:18 +00:00
David E. O'Brien
9565e1fac5 nfe_stop() requires lock to be held when calling. 2006-11-26 23:11:53 +00:00
David E. O'Brien
9ae2249db2 Missed two nits in rev 1.7. 2006-11-17 16:49:40 +00:00
David E. O'Brien
f220c6a2f9 style(9) 2006-10-19 10:04:46 +00:00
David E. O'Brien
2c3adf6127 style(9) cleanup. 2006-10-19 10:01:26 +00:00
David E. O'Brien
3cb32d8ab3 Correct the WOL magic value.
Submitted by:	Peer Chen at nVIDIA
2006-10-16 20:33:23 +00:00
David E. O'Brien
6bec396750 Try to be more precise in identifying the various nForce networking adapters. 2006-10-16 16:36:29 +00:00
Andre Oppermann
78ba57b9e1 Move ethernet VLAN tags from mtags to its own mbuf packet header field
m_pkthdr.ether_vlan.  The presence of the M_VLANTAG flag on the mbuf
signifies the presence and validity of its content.

Drivers that support hardware VLAN tag stripping fill in the received
VLAN tag (containing both vlan and priority information) into the
ether_vtag mbuf packet header field:

	m->m_pkthdr.ether_vtag = vlan_id;	/* ntohs()? */
	m->m_flags |= M_VLANTAG;

to mark the packet m with the specified VLAN tag.

On output the driver should check the mbuf for the M_VLANTAG flag to
see if a VLAN tag is present and valid:

	if (m->m_flags & M_VLANTAG) {
		... = m->m_pkthdr.ether_vtag;	/* htons()? */
		... pass tag to hardware ...
	}

VLAN tags are stored in host byte order.  Byte swapping may be necessary.

(Note: This driver conversion was mechanic and did not add or remove any
byte swapping in the drivers.)

Remove zone_mtag_vlan UMA zone and MTAG_VLAN definition.  No more tag
memory allocation have to be done.

Reviewed by:	thompsa, yar
Sponsored by:	TCP/IP Optimization Fundraise 2005
2006-09-17 13:33:30 +00:00
David E. O'Brien
3e232000c0 Add support for MCP61 and MCP65 adaptors.
Submitted by:	Peer Chen at nVIDIA
2006-09-11 07:31:55 +00:00
Ruslan Ermilov
d0220c83e1 Fix alignment of RX bufs DMA map to be realistic. Maybe it works on
i386 (I don't know) but on amd64 at hand here, it paniced early at
boot.

(I'm pretty sure that PAGE_SIZE here was miscopied from another place
during porting, where in OpenBSD bus_dmamem_alloc() is used, but there
PAGE_SIZE means completely different thing.)
2006-08-14 15:35:43 +00:00
David E. O'Brien
bfc788c283 Add a pure open source nForce Ethernet driver, under BSDL.
This driver was ported from OpenBSD by Shigeaki Tagashira
<shigeaki@se.hiroshima-u.ac.jp> and posted at
http://www.se.hiroshima-u.ac.jp/~shigeaki/software/freebsd-nfe.html
It was additionally cleaned up by me.
It is still a work-in-progress and thus is purposefully not in GENERIC.
And it conflicts with nve(4), so only one should be loaded.
2006-06-26 23:41:07 +00:00
David E. O'Brien
257c55772d Import the nfe (nForce Ethernet) driver from OpenBSD.
This is a pure open source NIC driver with a BSD license.
These bits were taken from the OpenBSD public CVS repository on 1-May-06.
2006-06-26 17:25:22 +00:00